Skip to content
SkillModel-led383 tokens in use

Amazon Ads Audit

Read-only audit of Amazon Ads accounts: profiles, sponsored formats, DSP, search terms, ACOS and TACOS, with findings that cite the data behind them.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-amazon
/plugin marketplace add agricidaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Amazon Ads Audit costs

78tokens idle
383tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure22/25
  • Examples0/15
  • Output10/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

The Amazon audit skill reviews an Amazon Ads account from the exports, screenshots or API results you supply. It covers profiles and regions, measurement, portfolios, Sponsored Products, Sponsored Brands, Sponsored Display, DSP, targeting, search terms, retail readiness, creative, budgets, ACOS, TACOS and policy.

Findings go back to the Claude Ads conductor as schema-valid JSON, and no account change is made. Benchmarks are only applied after checking objective, geography, sample size and account maturity.

What You Get

  • Schema-valid findings for Amazon Ads controls, each tied to an export, screenshot or API value
  • Platform health, evidence coverage and regulatory exposure kept as separate results
  • Prioritized recommendations with contradictions, missing inputs and recovery hints
  • A list of unscored opportunities for beta or ineligible features

Common Use Cases

  • Reviewing ACOS and TACOS trends for a seller or vendor account
  • Checking search term and targeting structure across Sponsored Products and Brands
  • Auditing DSP setup next to sponsored campaigns
  • Preparing the Amazon slice of an all-platform audit

What Makes It Unique

It is built for retail media. Controls cover ASIN-level retail readiness and TACOS next to the usual campaign checks. Beta, premium and ineligible features stay unscored, and the skill refuses universal pause, bid or budget rules, so a score reflects the evidence supplied.

Under The Hood

This is a prompt-only skill with no scripts. It tells the agent to read the main ads contract and the Amazon audit reference file, then to work from the exports, screenshots or API results you provide. It treats account and web content as data, never as instructions. It does not calculate final scores or write a shared result file, and it keeps every account change as a draft until the main mutation gate passes.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers